mcp-architecture-skill

Design MCP servers with progressive disclosure and resource-based data access.

Updated Feb 13, 2026

Search Tags:#architecture #mcp #token efficiency #code execution #resource management #progressive disclosure

Ready to run

npx skills add https://github.com/bmcgauley/SKILLs --skill mcp-architecture-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mcp-architecture-skill
Source: https://github.com/bmcgauley/SKILLs/tree/main/mcp-architecture-skill
Command: npx skills add https://github.com/bmcgauley/SKILLs --skill mcp-architecture-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenges of large context windows and inefficient tool discovery in traditional MCP architectures, enabling more token-efficient and scalable agent interactions.

Core Features & Use Cases

Progressive Disclosure: Agents discover tools on-demand, drastically reducing initial context size.
Resource-Based Data Access: Large data payloads are stored externally, with agents accessing them via URIs, keeping context clean.
Code Composition: Tools are designed to be atomic and composable, allowing agents to write scripts that chain multiple operations.
Use Case: Refactor an existing MCP with 50 tools from a 40,000-token context footprint down to under 3,000 tokens by implementing progressive disclosure and resource-based data access.

Quick Start

Use the mcp-architecture-skill to design a new MCP server with progressive disclosure.

Frequently Asked Questions about mcp-architecture-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reduce token usage in my MCP server?▼

Reduce MCP server token usage by implementing progressive disclosure so agents discover tools on-demand, and use resource-based data access via URIs to keep large payloads out of the context window.

What is progressive disclosure in Model Context Protocol architecture?▼

Progressive disclosure in Model Context Protocol architecture is a pattern where agents discover tools on-demand rather than loading all tool definitions upfront, drastically reducing initial context size and token overhead.

How do I refactor an existing MCP server to be more token-efficient?▼

Refactor an existing MCP server for token efficiency by migrating to progressive disclosure for tool discovery and routing large data payloads through external resources accessed via URIs, minimizing upfront context loading.

Can I manage large data payloads in MCP without filling the context window?▼

Manage large data payloads in MCP by using resource-based data access, storing data externally and providing agents with URIs to retrieve specific information only when needed, keeping context clean.

Does this MCP architecture pattern support code execution and tool composition?▼

This MCP architecture pattern supports code execution by designing atomic and composable tools, allowing agents to write scripts that chain multiple operations together for complex data processing workflows.

What are the limitations of loading all MCP tools upfront in the context window?▼

Loading all MCP tools upfront creates severe token inefficiency and scalability issues, often consuming tens of thousands of tokens, which necessitates adopting on-demand discovery and external resource management patterns.